Skip to main content
placeholder image

A Joint Local and Global Deep Metric Learning Method for Caricature Recognition

Journal Article


Abstract


  • Caricature recognition is a novel, interesting, yet challenging problem. Due to the exaggeration and distortion, there is a large cross-modal gap between photographs and caricatures, making it nontrivial to match the features of photographs and caricatures. To address the problem, a joint local and global metric learning method (LGDML) is proposed. First, joint local and global feature representation is learnt with convolutional neural networks to find both discriminant features of local facial parts and global distinctive features of the whole face. Next, in order to fuse the local and global similarities of features, a unified feature representation and similarity measure learning framework is proposed. Various methods are evaluated on the caricature recognition task. We have verified that both local and global features are crucial for caricature recognition. Moreover, experimental results show that, compared with the state-of-the-art methods, LGDML can obtain superior performance in terms of Rank-1 and Rank-10.

Authors


  •   Li, Wenbin (external author)
  •   Huo, Jing (external author)
  •   Shi, Yinghuan (external author)
  •   Gao, Yang (external author)
  •   Wang, Lei
  •   Luo, Jiebo (external author)

Publication Date


  • 2019

Citation


  • Li, W., Huo, J., Shi, Y., Gao, Y., Wang, L. & Luo, J. (2019). A Joint Local and Global Deep Metric Learning Method for Caricature Recognition. Lecture Notes in Computer Science, 11364 240-256. Perth, Australia Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision

Scopus Eid


  • 2-s2.0-85066876806

Number Of Pages


  • 16

Start Page


  • 240

End Page


  • 256

Volume


  • 11364

Place Of Publication


  • Germany

Abstract


  • Caricature recognition is a novel, interesting, yet challenging problem. Due to the exaggeration and distortion, there is a large cross-modal gap between photographs and caricatures, making it nontrivial to match the features of photographs and caricatures. To address the problem, a joint local and global metric learning method (LGDML) is proposed. First, joint local and global feature representation is learnt with convolutional neural networks to find both discriminant features of local facial parts and global distinctive features of the whole face. Next, in order to fuse the local and global similarities of features, a unified feature representation and similarity measure learning framework is proposed. Various methods are evaluated on the caricature recognition task. We have verified that both local and global features are crucial for caricature recognition. Moreover, experimental results show that, compared with the state-of-the-art methods, LGDML can obtain superior performance in terms of Rank-1 and Rank-10.

Authors


  •   Li, Wenbin (external author)
  •   Huo, Jing (external author)
  •   Shi, Yinghuan (external author)
  •   Gao, Yang (external author)
  •   Wang, Lei
  •   Luo, Jiebo (external author)

Publication Date


  • 2019

Citation


  • Li, W., Huo, J., Shi, Y., Gao, Y., Wang, L. & Luo, J. (2019). A Joint Local and Global Deep Metric Learning Method for Caricature Recognition. Lecture Notes in Computer Science, 11364 240-256. Perth, Australia Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision

Scopus Eid


  • 2-s2.0-85066876806

Number Of Pages


  • 16

Start Page


  • 240

End Page


  • 256

Volume


  • 11364

Place Of Publication


  • Germany